That's the exaone I have in my work bag too!
May 17, 2025 at 11:01 PM
That's the exaone I have in my work bag too!
LG AI Research's EXAONE Deep 2.4B, 7.8B, and 32B.
✔ Math – EXAONE Deep 32B Outperforms Competitors in High-Difficulty Math Benchmarks Even at Just 5% of Their Size
✔ Science & Coding – EXAONE Deep 7.8B & 2.4B Achieve Dominant Performance, Ranking #1 Across All Key Benchmarks
✔ Math – EXAONE Deep 32B Outperforms Competitors in High-Difficulty Math Benchmarks Even at Just 5% of Their Size
✔ Science & Coding – EXAONE Deep 7.8B & 2.4B Achieve Dominant Performance, Ranking #1 Across All Key Benchmarks
March 18, 2025 at 4:47 PM
LG AI Research's EXAONE Deep 2.4B, 7.8B, and 32B.
✔ Math – EXAONE Deep 32B Outperforms Competitors in High-Difficulty Math Benchmarks Even at Just 5% of Their Size
✔ Science & Coding – EXAONE Deep 7.8B & 2.4B Achieve Dominant Performance, Ranking #1 Across All Key Benchmarks
✔ Math – EXAONE Deep 32B Outperforms Competitors in High-Difficulty Math Benchmarks Even at Just 5% of Their Size
✔ Science & Coding – EXAONE Deep 7.8B & 2.4B Achieve Dominant Performance, Ranking #1 Across All Key Benchmarks
Oh wow, LG just released their own open source* LLM. If their published benchmarks are accurate, the 32B model is at least on par with Qwen2.5 (which is already an incredibly strong model), if not better.
www.lgresearch.ai/blog/view?se...
huggingface.co/LGAI-EXAONE
* open weights
www.lgresearch.ai/blog/view?se...
huggingface.co/LGAI-EXAONE
* open weights
Open-sourcing Three EXAONE 3.5 Models : Frontier-level Model, Top-tier Performance in Instruction Following and Long Context Capabilities - LG AI Research BLOG
www.lgresearch.ai
December 9, 2024 at 5:10 AM
Oh wow, LG just released their own open source* LLM. If their published benchmarks are accurate, the 32B model is at least on par with Qwen2.5 (which is already an incredibly strong model), if not better.
www.lgresearch.ai/blog/view?se...
huggingface.co/LGAI-EXAONE
* open weights
www.lgresearch.ai/blog/view?se...
huggingface.co/LGAI-EXAONE
* open weights
Today I learned about the GPU-poor LLM arena.
It's interesting as the models ranked there usually fit inside 4GB VRAM or less and run relatively well without GPU as well.
EXAONE from LG is on the lead. I tested the 3B model before and it did well for its size.
Here's the link:
It's interesting as the models ranked there usually fit inside 4GB VRAM or less and run relatively well without GPU as well.
EXAONE from LG is on the lead. I tested the 3B model before and it did well for its size.
Here's the link:
December 28, 2024 at 7:33 PM
Today I learned about the GPU-poor LLM arena.
It's interesting as the models ranked there usually fit inside 4GB VRAM or less and run relatively well without GPU as well.
EXAONE from LG is on the lead. I tested the 3B model before and it did well for its size.
Here's the link:
It's interesting as the models ranked there usually fit inside 4GB VRAM or less and run relatively well without GPU as well.
EXAONE from LG is on the lead. I tested the 3B model before and it did well for its size.
Here's the link:
LG launched three open-source EXAONE-3.5 LLMs (2.4B, 7.8B, 32B).
They claim to be significantly better than Qwen 2.5 and with large context capabilities.
I tried the 2.4B model, and it's quite good considering its size.
Soon we'll have LLMs running in our fridges! 🤖
They claim to be significantly better than Qwen 2.5 and with large context capabilities.
I tried the 2.4B model, and it's quite good considering its size.
Soon we'll have LLMs running in our fridges! 🤖
December 9, 2024 at 9:32 PM
LG launched three open-source EXAONE-3.5 LLMs (2.4B, 7.8B, 32B).
They claim to be significantly better than Qwen 2.5 and with large context capabilities.
I tried the 2.4B model, and it's quite good considering its size.
Soon we'll have LLMs running in our fridges! 🤖
They claim to be significantly better than Qwen 2.5 and with large context capabilities.
I tried the 2.4B model, and it's quite good considering its size.
Soon we'll have LLMs running in our fridges! 🤖
EXAONE 4.0 32B
not sure how i missed this — a 32B that’s up with Opus with thinking
i guess we have a new lab to watch?
artificialanalysis.ai/models/exaon...
not sure how i missed this — a 32B that’s up with Opus with thinking
i guess we have a new lab to watch?
artificialanalysis.ai/models/exaon...
July 31, 2025 at 12:05 PM
EXAONE 4.0 32B
not sure how i missed this — a 32B that’s up with Opus with thinking
i guess we have a new lab to watch?
artificialanalysis.ai/models/exaon...
not sure how i missed this — a 32B that’s up with Opus with thinking
i guess we have a new lab to watch?
artificialanalysis.ai/models/exaon...
Lee, Han, Seo, Kang, Lee, Lim, Kang, Choi, Kim, Yoo, Lee, Ahn: EXAONE Demand 1.0: A Time Series Foundation Model for Demand Forecasting https://arxiv.org/abs/2609.30880 https://arxiv.org/pdf/2609.30880 https://arxiv.org/html/2609.30880
September 28, 2026 at 6:39 AM
Lee, Han, Seo, Kang, Lee, Lim, Kang, Choi, Kim, Yoo, Lee, Ahn: EXAONE Demand 1.0: A Time Series Foundation Model for Demand Forecasting https://arxiv.org/abs/2609.30880 https://arxiv.org/pdf/2609.30880 https://arxiv.org/html/2609.30880
EXAONE Deep 공개 ━ Reasoning AI의 새로운 기준을 세우다 - LG AI Research BLOG
www.lgresearch.ai/blog/view?se...
- LG AI연구원이 새로운 추론 특화 AI 모델 'EXAONE Deep'을 공개
- 이 모델은 수학, 과학, 코딩 영역에서 뛰어난 추론 능력을 갖추었으며, 32B 버전은 국내 자체 모델 중 최고 성능(MMLU 83.0점)을 입증
(계속)
www.lgresearch.ai/blog/view?se...
- LG AI연구원이 새로운 추론 특화 AI 모델 'EXAONE Deep'을 공개
- 이 모델은 수학, 과학, 코딩 영역에서 뛰어난 추론 능력을 갖추었으며, 32B 버전은 국내 자체 모델 중 최고 성능(MMLU 83.0점)을 입증
(계속)
EXAONE Deep 공개 ━ Reasoning AI의 새로운 기준을 세우다 - LG AI Research BLOG
www.lgresearch.ai
March 18, 2025 at 10:20 AM
EXAONE Deep 공개 ━ Reasoning AI의 새로운 기준을 세우다 - LG AI Research BLOG
www.lgresearch.ai/blog/view?se...
- LG AI연구원이 새로운 추론 특화 AI 모델 'EXAONE Deep'을 공개
- 이 모델은 수학, 과학, 코딩 영역에서 뛰어난 추론 능력을 갖추었으며, 32B 버전은 국내 자체 모델 중 최고 성능(MMLU 83.0점)을 입증
(계속)
www.lgresearch.ai/blog/view?se...
- LG AI연구원이 새로운 추론 특화 AI 모델 'EXAONE Deep'을 공개
- 이 모델은 수학, 과학, 코딩 영역에서 뛰어난 추론 능력을 갖추었으며, 32B 버전은 국내 자체 모델 중 최고 성능(MMLU 83.0점)을 입증
(계속)
there's EXAONE, but they don't seem to be near the open Pareto frontier, judging by their benchmarks? huggingface.co/LGAI-EXAONE/...
but yes, they're in the game, too! hmm, I wonder if there's a list of unique pretrains anywhere
but yes, they're in the game, too! hmm, I wonder if there's a list of unique pretrains anywhere
June 17, 2026 at 4:28 AM
there's EXAONE, but they don't seem to be near the open Pareto frontier, judging by their benchmarks? huggingface.co/LGAI-EXAONE/...
but yes, they're in the game, too! hmm, I wonder if there's a list of unique pretrains anywhere
but yes, they're in the game, too! hmm, I wonder if there's a list of unique pretrains anywhere
EXAONE 3.5 is on Hugging Face 🤗
💬 How does it compare to SOTA? What are the contributions? Chat with the paper and find out:
🤗 Chat: huggingface.co/spaces/hugg...
🤗 Paper-page: huggingface.co/papers/2412...
🤗 Models: huggingface.co/LGAI-EXAONE...
🤗 Space: huggingface.co/spaces/LGAI...
💬 How does it compare to SOTA? What are the contributions? Chat with the paper and find out:
🤗 Chat: huggingface.co/spaces/hugg...
🤗 Paper-page: huggingface.co/papers/2412...
🤗 Models: huggingface.co/LGAI-EXAONE...
🤗 Space: huggingface.co/spaces/LGAI...
December 9, 2024 at 6:38 PM
EXAONE 3.5 is on Hugging Face 🤗
💬 How does it compare to SOTA? What are the contributions? Chat with the paper and find out:
🤗 Chat: huggingface.co/spaces/hugg...
🤗 Paper-page: huggingface.co/papers/2412...
🤗 Models: huggingface.co/LGAI-EXAONE...
🤗 Space: huggingface.co/spaces/LGAI...
💬 How does it compare to SOTA? What are the contributions? Chat with the paper and find out:
🤗 Chat: huggingface.co/spaces/hugg...
🤗 Paper-page: huggingface.co/papers/2412...
🤗 Models: huggingface.co/LGAI-EXAONE...
🤗 Space: huggingface.co/spaces/LGAI...
1️⃣ LG se mete en la IA para razonar... y va en serio 🧵👇
Han presentado EXAONE Deep: modelos open source especializados en matemáticas, ciencia y código.
Han presentado EXAONE Deep: modelos open source especializados en matemáticas, ciencia y código.
April 2, 2025 at 6:32 PM
1️⃣ LG se mete en la IA para razonar... y va en serio 🧵👇
Han presentado EXAONE Deep: modelos open source especializados en matemáticas, ciencia y código.
Han presentado EXAONE Deep: modelos open source especializados en matemáticas, ciencia y código.
EXAONE 4.5: LG's Open VLM Beats GPT-5-mini on STEM
https://awesomeagents.ai/news/lg-exaone-4-5-open-weight-multimodal/
#OpenSource #Llm #Benchmarks
https://awesomeagents.ai/news/lg-exaone-4-5-open-weight-multimodal/
#OpenSource #Llm #Benchmarks
EXAONE 4.5: LG's Open VLM Beats GPT-5-mini on STEM
LG AI Research released EXAONE 4.5, a 33B open-weight vision-language model that posts higher STEM scores than GPT-5-mini and Claude 4.5 Sonnet - but a non-commercial license caps its real-world reach.
awesomeagents.ai
April 10, 2026 at 10:01 AM
EXAONE 4.5: LG's Open VLM Beats GPT-5-mini on STEM
https://awesomeagents.ai/news/lg-exaone-4-5-open-weight-multimodal/
#OpenSource #Llm #Benchmarks
https://awesomeagents.ai/news/lg-exaone-4-5-open-weight-multimodal/
#OpenSource #Llm #Benchmarks
Servirán modelos abiertos desarrollados por el estado (A.X K2) y compañías coreanas (Solar, EXAONE, Motif), con 512 GPUs B200 proporcionadas por el estado coreano.
Una verdadera plataforma soberana y pública, al servicio de todos los ciudadanos.
Una verdadera plataforma soberana y pública, al servicio de todos los ciudadanos.
September 10, 2026 at 11:34 AM
Servirán modelos abiertos desarrollados por el estado (A.X K2) y compañías coreanas (Solar, EXAONE, Motif), con 512 GPUs B200 proporcionadas por el estado coreano.
Una verdadera plataforma soberana y pública, al servicio de todos los ciudadanos.
Una verdadera plataforma soberana y pública, al servicio de todos los ciudadanos.
LG unveils upgraded version of Exaone AI model with advanced features
yespunjab.com?p=71185
#LGAIResearch #ExaoneAI #AIModel #ArtificialIntelligence #OpenSourceAI #MultimodalAI #AIResearch #AIDevelopment #Exaone #LG #LGAI
yespunjab.com?p=71185
#LGAIResearch #ExaoneAI #AIModel #ArtificialIntelligence #OpenSourceAI #MultimodalAI #AIResearch #AIDevelopment #Exaone #LG #LGAI
LG unveils upgraded version of Exaone AI model with advanced features - Yes Punjab News
LG AI Research has unveiled the Exaone 3.5, an upgraded multimodal AI model offering improved performance and cost efficiency. The model, released as open source, supports various research purposes an...
yespunjab.com
December 9, 2024 at 8:28 AM
LG unveils upgraded version of Exaone AI model with advanced features
yespunjab.com?p=71185
#LGAIResearch #ExaoneAI #AIModel #ArtificialIntelligence #OpenSourceAI #MultimodalAI #AIResearch #AIDevelopment #Exaone #LG #LGAI
yespunjab.com?p=71185
#LGAIResearch #ExaoneAI #AIModel #ArtificialIntelligence #OpenSourceAI #MultimodalAI #AIResearch #AIDevelopment #Exaone #LG #LGAI
LG releases hybrid AI model - EXAONE 4.0
Key performance indicators :
- MMLU-Pro (knowledge and reasoning) : 81.8
- LiveCodeBench v6 (coding) : 66.7
- GPQA-Diamond(science) : 75.4
- AIME 2025 (math) : 85.3
Key performance indicators :
- MMLU-Pro (knowledge and reasoning) : 81.8
- LiveCodeBench v6 (coding) : 66.7
- GPQA-Diamond(science) : 75.4
- AIME 2025 (math) : 85.3
July 16, 2025 at 1:26 AM
LG releases hybrid AI model - EXAONE 4.0
Key performance indicators :
- MMLU-Pro (knowledge and reasoning) : 81.8
- LiveCodeBench v6 (coding) : 66.7
- GPQA-Diamond(science) : 75.4
- AIME 2025 (math) : 85.3
Key performance indicators :
- MMLU-Pro (knowledge and reasoning) : 81.8
- LiveCodeBench v6 (coding) : 66.7
- GPQA-Diamond(science) : 75.4
- AIME 2025 (math) : 85.3
I am excited to share with my followers here:
"LG AI Research is now unveiling EXAONE Deep, a reasoning AI with enhanced reasoning capabilities capable of competing with these industry-leading models. "
"LG AI Research is now unveiling EXAONE Deep, a reasoning AI with enhanced reasoning capabilities capable of competing with these industry-leading models. "
EXAONE Deep: Reasoning Enhanced Language Models
We present EXAONE Deep series, which exhibits superior capabilities in various reasoning tasks, including math and coding benchmarks. We train our models mainly on the reasoning-specialized dataset th...
arxiv.org
March 21, 2025 at 10:32 AM
I am excited to share with my followers here:
"LG AI Research is now unveiling EXAONE Deep, a reasoning AI with enhanced reasoning capabilities capable of competing with these industry-leading models. "
"LG AI Research is now unveiling EXAONE Deep, a reasoning AI with enhanced reasoning capabilities capable of competing with these industry-leading models. "
gemma 4랑 exaone 괜찮았던거 같습니다.
June 9, 2026 at 3:38 AM
gemma 4랑 exaone 괜찮았던거 같습니다.
Does letta support the latest South Korean model? huggingface.co/LGAI-EXAONE/...
LGAI-EXAONE/EXAONE-4.0.1-32B · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
December 16, 2025 at 2:34 AM
Does letta support the latest South Korean model? huggingface.co/LGAI-EXAONE/...
WelsonJS 프로젝트에 LG AI 연구원에서 만든 LG EXAONE 모델 연동을 추가하였습니다.
이제 시스템 자동화, 오피스 자동화를 국내 연구진이 개발한 AI와 함께 해보세요!
이제 시스템 자동화, 오피스 자동화를 국내 연구진이 개발한 AI와 함께 해보세요!
January 19, 2026 at 6:12 AM
WelsonJS 프로젝트에 LG AI 연구원에서 만든 LG EXAONE 모델 연동을 추가하였습니다.
이제 시스템 자동화, 오피스 자동화를 국내 연구진이 개발한 AI와 함께 해보세요!
이제 시스템 자동화, 오피스 자동화를 국내 연구진이 개발한 AI와 함께 해보세요!
"LG AI’s EXAONE is regarded as the leading sovereign AI model in South Korea. It won’t be used just within LG. It will be one of the main AI models used in the Korean AI ecosystem"
Instead of selling to Meta, AI chip startup FuriosaAI signed a huge customer
Instead of selling to Meta, AI chip startup FuriosaAI signed a huge customer | TechCrunch
South Korean AI chip startup FuriosaAI announced a partnership on Tuesday to supply its AI chip, RNGD, to enterprises using LG AI Research's recently
techcrunch.com
July 22, 2025 at 5:15 AM
"LG AI’s EXAONE is regarded as the leading sovereign AI model in South Korea. It won’t be used just within LG. It will be one of the main AI models used in the Korean AI ecosystem"
LG에서 공개한 LLM모델 EXAONE-3.0-7.8B-Instruct의 답변.
여러분 이게 한국의 현실입니다. 나경원이 미워도 이건 아닙니다~~~ 한동훈 질문 아닙니다.
여러분 이게 한국의 현실입니다. 나경원이 미워도 이건 아닙니다~~~ 한동훈 질문 아닙니다.
August 12, 2024 at 11:57 PM
LG에서 공개한 LLM모델 EXAONE-3.0-7.8B-Instruct의 답변.
여러분 이게 한국의 현실입니다. 나경원이 미워도 이건 아닙니다~~~ 한동훈 질문 아닙니다.
여러분 이게 한국의 현실입니다. 나경원이 미워도 이건 아닙니다~~~ 한동훈 질문 아닙니다.